Dexio

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare non-read-only, non-idempotent, non-destructive behavior, and the description adds the meaningful auto-create-if-missing behavior and append-on-new-line semantics that the annotations do not convey. It omits auth/permission requirements and what happens on concurrent appends.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with the core action front-loaded and no filler. The trailing 'For logs and running lists' is the only semi-optional line, but it is short and useful for routing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a non-idempotent mutation with no output schema and an auto-create side effect, the description covers the essential operation but says nothing about failure modes, permission needs, or result confirmation — leaving gaps an agent would want filled.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 60%, with note, agent, and workspace documented in the schema itself. The description explains what 'text' and 'path' imply only indirectly and adds no syntax, format, or constraint detail beyond the schema — the baseline level when the schema does most of the work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Add text to the end of a page on a new line') plus the upsert nuance ('creating the page if needed'). Clear enough to distinguish from read_page or list_pages, though it never contrasts itself with the closer siblings write_page, edit_page, or change_pages.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'For logs and running lists' hints at the intended scenario but gives no explicit when-to-use conditions or alternatives, which matters given siblings like edit_page, write_page, and change_pages that also modify page content.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description is otherwise rich: it discloses atomicity ('all or none'), ordered execution, a 200-change cap, and that dry_run reports pending changes and broken links while writing nothing. However it advertises a 'delete' operation while the annotations declare destructiveHint=false, which is a factual mismatch for an operation that removes pages. That contradiction with structured data caps this dimension low despite the added detail.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loads the key scoping facts (200-change limit, atomicity, op list). The phrasing is a little telegraphic and the dry_run sentence is somewhat clipped, but there is no filler or repetition of schema content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description covers what an agent most needs: ordering, atomic failure semantics, the cap, the supported ops, and what dry_run returns (would-change set plus broken-link warnings). It stops short of describing error reporting granularity for rejected batches, but is largely complete for a 5-parameter mutation tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 60%, so the schema already documents most fields. The description compensates by explaining the batch semantics of the changes array (up to 200, ordered, all-or-none) and clearly defining what dry_run does, which is a parameter the schema leaves bare. It also ties each op to its corresponding single-page tool rather than re-listing per-field syntax.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete verb and resource (apply up to 200 page changes as one atomic step) and enumerates the exact operations supported: write, edit, append, delete, move. It also distinguishes the tool from its single-page siblings by noting each change carries 'its one-page tool's fields', so an agent can tell this apart from write_page/edit_page/delete_page/move_page without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It implies the batch use case (multiple changes, run in order, all or none) and hints at the one-page tool mapping, plus a dry_run preview mode. But it never explicitly states when to prefer this over the individual write_page/edit_page/delete_page tools, nor does it state exclusions or prerequisites (e.g. permissions, conflicting concurrent edits).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered; the description adds genuine extra context by stating deletion is permanent and that files keep no history, which contrasts with the page_history sibling. It does not mention permissions or whether references are cascaded, so it stops short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the action and immediately followed by the critical permanence caveat. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive tool whose annotations already flag destruction and idempotency, the description conveys the key irreversible consequence and no output schema is needed. However, the undocumented 'path' parameter and the absence of any permission or confirmation context leave real gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 50%: 'workspace' is documented in the schema, but 'path' has no description anywhere, and the description text says nothing about either parameter. It fails to compensate for the undocumented required path argument.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Delete an uploaded file'), and 'uploaded file' separates it from the sibling delete_page. It never names sibling tools directly, so differentiation relies on the resource noun rather than explicit routing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no mention of alternatives (e.g., delete_page for pages), and no prerequisites or warnings about confirming before calling. Usage is only implied by the verb.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds genuinely non-structured behavior: history is retained, the result includes restore instructions, and the call reports pages whose links are now broken — all side-effect/reversibility context the annotations cannot express. It stops short of noting permission requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, zero filler, with the core action front-loaded and the two behavioral consequences following in priority order. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly explains what the result contains (restore info, newly broken links), which is the most valuable gap to fill. It is reasonably complete for a mutation tool, though it omits auth/permission expectations and the concurrency role of base_version.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description mentions no parameters at all, and schema description coverage is only 60% (path and base_version carry no schema description). The agent gets no help on what base_version means (likely optimistic-concurrency guard) or the format of path, so the description fails to compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Delete a page') and immediately scopes it against siblings: it is a page (not a file, unlike delete_file) and it is non-destructive to history. An agent can distinguish this from edit_page, change_pages, or set_visibility without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use or when-not-to-use guidance is given. Nothing tells the agent to prefer set_visibility or change_pages over deletion, nor what preconditions (permissions, base_version conflicts) apply. Usage is only inferable from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the bar is lower, and the description still adds real behavior: uniqueness constraints on old_text, the replace_all escape hatch, section scoping including the heading, and the fact that empty new_text deletes content. It does not mention versioning/concurrency risk or the page_history recovery path, and the deletion behavior sits in mild tension with destructiveHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences, front-loaded with the core action before the parameter rules, and every clause carries operational meaning (uniqueness, scoping, deletion). No filler or restatement of the title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter mutation tool with no output schema and low schema coverage, the edit-mode semantics are well covered but important context is absent: what base_version does, how workspace targets another space, and that agent must identify the caller. An agent could call it correctly in the common case but would miss concurrency and cross-workspace behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33%, and the description supplies semantics for four of nine parameters (old_text, new_text, replace_all, section), including their interaction rules. It says nothing about path, agent, note, workspace, or base_version — notably base_version, whose optimistic-concurrency meaning is documented nowhere.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ("Change part of a page") and the phrase "part of a page" implicitly separates it from whole-page writers like write_page and append_page. It never names those siblings explicitly, so an agent must infer the boundary from the wording alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly governs mode selection within the tool: old_text for exact-string replacement, section alone for whole-section replacement, both together for scoped replacement, empty new_text to delete. However it gives no guidance on when to reach for edit_page versus write_page, append_page, or change_pages, so cross-tool routing is left implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the useful note that results include size, type and last change, but says nothing about pagination, result limits, or ordering.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single tight sentence with the resource front-loaded and the scope qualifier and returned fields appended without waste. Nothing could be removed without losing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the burden of describing returns and does so partially (size, type, last change), but omits pagination, ordering and empty-result behavior. For a two-param read-only listing tool with annotation coverage, this is adequate but incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%: the 'workspace' param is documented in the schema, but 'folder' has no schema description. The description's 'or one folder's' hints that folder scopes the listing, but it never states that an empty folder means the whole wiki, so it only partially compensates for the gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb+resource ('List the wiki's uploaded files') with scope clarified ('or one folder's') and return fields named (size, type, last change). It clearly distinguishes the file listing from the sibling list_pages, though it never names that sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage through the 'or one folder's' phrasing, but gives no explicit when-to-use/when-not guidance and never mentions alternatives such as search_pages or list_pages for navigating the wiki. The agent must infer when this tool beats its siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover readOnly/idempotent/non-destructive/closed-world, so the safety profile is free. The description adds real behavioral context beyond them: page size of 200, the next_offset continuation signal, subfolder page counts, and how the one-line description is derived (frontmatter description, else first sentence). No auth or rate-limit notes, hence not a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two dense sentences with no filler, and the primary purpose plus scope lead the text before pagination details. The clause stacking (fields, ordering, page size, continuation, sibling pointer) is heavy but each clause carries information an agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description correctly takes on the burden of describing the return shape (title, description, word count, last change, path order, next_offset, subfolder counts), which is thorough. It is slightly thin on the limit/offset parameters and on how to resume a listing beyond the mention of next_offset.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25% (only 'workspace' is documented), so the description must compensate. It does partially: 'one folder's' clarifies the folder parameter, '200 at a time' implies the default limit, and 'next_offset' ties to the offset parameter. However limit and offset are never named or bounded, so the gap is only partly closed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List the wiki's pages, or one folder's') plus the exact fields returned and the ordering, and explicitly routes file listings to the sibling list_files. An agent can distinguish it from list_files, search_pages and read_page without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context (whole wiki vs a single folder) and names the alternative for a related need ('Uploaded files are in list_files'), and explains pagination follow-up via next_offset. It stops short of stating when to prefer search_pages over a full listing, so it is not fully explicit about all alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover readOnly, idempotent, non-destructive, and closed-world, so the bar is lower. The description still adds real behavioral value: it explains the identity model ('acting as its person') and, critically, which entries are read-write versus read-only and with what they share pages. That access-level detail is not in any structured field.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, both carrying information, with the resource and identity framing front-loaded. The first sentence is dense with stacked parentheticals, which makes it slightly harder to parse, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no parameters, no output schema, and annotations already declaring the safety profile, the description supplies the missing pieces: what the list contains, how entries differ by permission, and how to consume the handles. It stops short of describing ordering or scale limits, but nothing essential is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the baseline is 4. The description does mention passing a handle as 'workspace' to other tools, but that pertains to downstream calls rather than this tool's own inputs, so no additional param semantics apply here.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description specifies the resource (workspaces reachable by this key) and enumerates the categories returned (this one, member workspaces, page-sharing workspaces), which clearly distinguishes it from page/file siblings like list_pages or list_files. It lacks an explicit verb like 'list', phrased as a fragment, which keeps it just below a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives practical workflow guidance — 'Pass one's handle as workspace to any tool to act there' — telling the agent what to do with the result. It does not name exclusions or alternate tools, but there is no obvious sibling alternative for enumerating workspaces, so context is clear without them.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this as a non-read-only, non-destructive, non-idempotent operation. The description adds genuinely new behavioural context beyond that: links to the page are rewritten (with an opt-out via update_links), and the call fails when new_path already exists. It stops short of stating permission requirements or whether the move is reversible.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences, front-loaded with the core action and followed by the two behavioural caveats. No filler; only the awkward line wrapping keeps it from being a model of brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no output schema, the description covers the two facts an agent most needs: the link-rewriting side effect and the collision failure. Annotations carry the safety profile. Missing only auth/permission expectations, which is a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50%; note, agent, and workspace are documented in-schema, while path and new_path are bare. The description partially compensates by explaining the effect of update_links and clarifying that path/new_path represent the current and target locations. Baseline 3 is appropriate given the mixed coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb pair and resource ('Rename or move a page') plus a side effect (link rewriting) and a failure condition. It is clear enough to distinguish from list/read siblings, though it never explicitly contrasts itself with edit_page or change_pages, which are the nearest neighbours.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the verb and the stated precondition ('Fails if new_path exists'), which tells the agent when the call will not succeed. However, there is no explicit guidance on when to prefer this over edit_page/change_pages or what prerequisites (permissions, existing source page) apply.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuine value on top: newest-first ordering and the fact that it works for deleted pages. It also enumerates the returned fields, which is meaningful context absent an output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The long parenthetical field list (when, op, agent, person, author, note, version) is informative but crammed mid-sentence, and the trailing fragment 'agent filters to one agent' reads awkwardly. Front-loads the core purpose but the middle is dense.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With four parameters, no output schema, and low schema coverage, the description does a fair job: it clarifies the optional path, the agent filter, and the return fields. Only limit handling and workspace semantics are left to the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25% (workspace only), so the description must compensate. It explains path semantics (omit for wiki-wide) and the agent filter, but says nothing about limit, and workspace meaning lives entirely in the schema. Partial compensation, not full.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States the resource precisely: a page's revisions newest-first, or, when path is omitted, the wiki's latest changes. The dual-mode behavior is clear enough to separate it from read_page and list_pages, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage by explaining that omitting path yields wiki-wide changes and that the agent parameter narrows to one agent. It never states when to prefer this over read_page/search_pages or gives any exclusion, so usage is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent, so the bar is lower, yet the description adds real behavior: the 128 KB per-read cap, next_offset continuation, and the header's version field that must be passed back as base_version for later writes. That concurrency-relevant detail is exactly the kind of context annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, each load-bearing: return shape first, then the partial-read modes, then the size/revision/file variants. No filler and the primary use case is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter tool with no output schema and near-zero schema coverage, the description covers the return contract, pagination, and every non-trivial parameter, so an agent can call it correctly. It stops just short of linking to sibling discovery tools or stating error behavior for missing paths.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 14%, so the description must compensate, and it does: limit/offset are explained as line ranges, outline and section as alternatives for partial reads, revision as a page_history lookup, and path as sometimes an uploaded-file path returning image or document text. Only workspace is left to the schema, which already documents it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Read a page') and immediately characterizes the return: a JSON header plus markdown text. It distinguishes itself from siblings like page_history (revisions) and the write tools by being the read path, and names the header fields it produces.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete conditions for each mode: outline=true for headings/line numbers, section for one heading, offset/limit for line ranges, revision for past versions, and uploaded file paths for images or document text. It does not explicitly route the agent to list_pages/search_pages for discovering a path, which is the one missing 'when-not' linkage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral detail beyond that: every word must match, common words are dropped, substrings count, results are ranked best-first, quoted text is exact, and results include matching lines with line numbers.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences with no filler; matching semantics and usage guidance are both packed in. Slightly better front-loading would put the "when to use" clause before the ranking rules, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter search tool with no output schema, the description compensates by stating the return shape (pages with matching lines and line numbers). Gaps remain around pagination/limit behavior, folder scoping, and case sensitivity, which an agent would have to infer from defaults.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 14% (just the workspace param), so the description must carry weight. It does explain query semantics (word matching, quoted/exact text) and what regex=true means, but it never mentions limit, folder, case_sensitive, or matches_per_page, leaving four parameters undocumented in both places.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Search the wiki's paths, titles and text") and immediately scopes what is searched. This is clearly distinguishable from siblings like list_pages, read_page and page_history, which enumerate or fetch rather than query by content.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete when-to-use direction: "Search before answering about the workspace and before creating a page." It also hints at the alternative mode of use via regex=true. It does not name a competing sibling (e.g., read_page for known pages) or state exclusions, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (idempotent, non-destructive), the description discloses that link pages are de-listed from search engines, that published content is publicly listed on dexio.wiki and copyable, that omitting visibility makes the call report without changing anything, and that parent-folder/wiki settings still apply to children. That is substantive effect-level context. It stops short of stating who is authorized to make these changes or any error behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The single paragraph is dense and mostly earns its place, but it opens by defining what visibility means instead of front-loading the action, and the inheritance sentence plus the closing 'for when the person asks for it' repeat context already implied. Structure is functional but not tight.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully notes that a call without visibility reports current state without changing it, and it explains the semantics of each mode and inheritance. Missing pieces are authorization requirements and failure modes, which is a modest gap for a security-sensitive setting tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 17%, so the description must carry the load, and it does: it defines all three visibility enum values in detail, maps kind to page/folder/wiki, explains the empty-path case, and notes title/description are needed for a published listing. Only the workspace parameter is left unaddressed in the description text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description conveys a specific resource and scope: visibility for a page, a folder (including everything under it), or the whole wiki when the path is empty, and 'or change it' implies the mutation. The verb itself is only implied rather than stated, and no sibling tool is named, so it falls short of the 5-level differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a conditional for the riskiest mode ('Opening something to the public is for when the person asks for it') and constrains 'published' to a folder or the wiki only, which is real usage guidance. However, it never contrasts this tool with alternatives such as change_pages or edit_page, nor states prerequisites, so guidance is implied rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With annotations covering only the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description supplies the behaviors that matter: the URL is one-time, valid for 15 minutes, has a 100 MB ceiling, and overwrites whatever exists at path. Overwrite semantics, expiry, and size limit are exactly the extra context annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the core action and then the mechanics. Every clause carries information — size cap, example path, shell command, expiry, overwrite behavior — with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a no-output-schema tool this covers the full round trip: what it returns (a URL), how to use it, and its constraints. It omits whether special permissions are needed and whether the returned URL should be treated as a secret, which would be the final useful details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75%, just under the high-coverage baseline, so the description must carry some load. It does: path is illustrated with a concrete example (raw/deck.pdf) and its significance explained (pages link to files by path). The note, agent, and workspace parameters are left entirely to their schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: get a one-time URL for uploading a file. It also bounds what can be uploaded (image, PDF, deck, up to 100 MB) and clarifies the two-step flow. It does not explicitly distinguish itself from siblings like write_page or list_files, so a 4 rather than a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete operational guidance: obtain the URL, then PUT with a shell command (curl -T FILE URL), and notes the URL is single-use and expires in 15 minutes. It never states when to prefer this tool over alternatives such as write_page for page content, so it stops short of full when/when-not routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description does add a genuinely useful behavioral distinction: broken links are 'the only problems' while the remaining categories are informational. It says nothing about cost, permissions, or pagination.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single dense run-on sentence loaded with parentheticals, so it is not well front-loaded or scannable. Every clause carries real content, so it is not padding, but the structure could be broken into the primary result plus a short list.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully enumerates the returned categories, which is exactly what the agent needs. Combined with the annotations covering safety, the definition is largely complete, missing only usage routing and any note on result size or cost.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33% (only 'workspace' is documented), so the description must compensate, and it largely does: it defines stale_days via 'past their stale_after date, or unchanged stale_days while pages they link to changed' and long_page_words via 'pages over long_page_words'. The definitions are slightly convoluted but they do give the parameters meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Check the wiki') and then enumerates precisely what the check reports, so an agent can tell it apart from list_pages/search_pages which just retrieve content. The purpose is clear, though the enumerated output list is long enough to blur the headline.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use or when-not guidance, and no alternatives are named despite many sibling read tools (list_pages, search_pages, page_history). The agent must infer that this is the diagnostic tool for detecting broken links.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false. The description adds real value beyond them: base_version provides optimistic-concurrency semantics ('makes the write fail if the page changed since you read it') and it discloses the whole-text replacement behavior. Still omits auth/permission or rate-limit context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with purpose, then routing, then the key parameter caveat. Every sentence earns its place with no filler. Slightly terse on the concurrency point but not padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a write tool with no output schema and annotations covering the safety profile, the description supplies the essential behaviors: create-vs-replace, the edit_page alternative, and base_version failure semantics. Gaps remain around permissions and the meaning of path/text, but the core invocation context is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50%; path, text, and base_version carry no schema description. The description compensates for only base_version (its concurrency role), leaving path and text unexplained and adding nothing about note/agent/workspace beyond what the schema already documents. Baseline 3 for partial coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Create a page or replace its whole text') and explicitly differentiates from the sibling edit_page. The dual create/overwrite framing is slightly muddled but an agent can still tell what this tool does without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit when-not rule: 'If a page on the topic exists, use edit_page.' Names the alternative, which is stronger than implied guidance. It stops short of 5 because it never mentions append_page, and the condition 'on the topic' is fuzzier than a path/identity check.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.